Open akfheaven opened 1 year ago
I was wondering about the same thing, @akfheaven curious if you've tried that.
It's possible, but probably you should mark input with some special symbols (at the end?) Like it happens when we make "[text]?" or "[text]!" instead of usual "[text]."
I've tried normal speech dataset and generated very natual voice. But how about training with emotional dataset? any one have a try?